切换语言

Create fine-tuning job

post https://api.openai.com/v1/fine_tuning/jobs

Creates a fine-tuning job which begins the process of creating a new model from a given dataset.source

Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete.source

Learn more about fine-tuningsource

Request body

model

stringsource

Required

The name of the model to fine-tune. You can select one of the supported models.source

training_file

stringsource

Required

The ID of an uploaded file that contains training data.source

See upload file for how to upload a file.source

Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose fine-tune.source

The contents of the file should differ depending on if the model uses the chat or completions format.source

See the fine-tuning guide for more details.source

hyperparameters

objectsource

Optional

The hyperparameters used for the fine-tuning job.source

suffix

string or nullsource

Optional
Defaults to null

A string of up to 64 characters that will be added to your fine-tuned model name.source

For example, a suffix of "custom-model-name" would produce a model name like ft:gpt-4o-mini:openai:custom-model-name:7p4lURel.source

validation_file

string or nullsource

Optional

The ID of an uploaded file that contains validation data.source

If you provide this file, the data is used to generate validation metrics periodically during fine-tuning. These metrics can be viewed in the fine-tuning results file. The same data should not be present in both train and validation files.source

Your dataset must be formatted as a JSONL file. You must upload your file with the purpose fine-tune.source

See the fine-tuning guide for more details.source

integrations

array or nullsource

Optional

A list of integrations to enable for your fine-tuning job.source

seed

integer or nullsource

Optional

The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. If a seed is not specified, one will be generated for you.source

Returns

A fine-tuning.job object.source

Example request
1
2
3
4
5
6
7
curl https://api.openai.com/v1/fine_tuning/jobs \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -d '{
    "training_file": "file-BK7bzQj3FfZFXr7DbL6xJwfo",
    "model": "gpt-4o-mini"
  }'
Response
1
2
3
4
5
6
7
8
9
10
11
12
{
  "object": "fine_tuning.job",
  "id": "ftjob-abc123",
  "model": "gpt-4o-mini-2024-07-18",
  "created_at": 1721764800,
  "fine_tuned_model": null,
  "organization_id": "org-123",
  "result_files": [],
  "status": "queued",
  "validation_file": null,
  "training_file": "file-abc123",
}